• Journal of Ocean Engineering and Technology
• /
• v.34 no.3
• /
• pp.167-179
• /
• 2020

Recently, the increasing importance of artificial intelligence (AI) technology has led to its increased use in various fields in the shipbuilding and marine industries. For example, typical scenarios for AI include production management, analyses of ships on a voyage, and motion prediction. Therefore, this study was conducted to predict a response amplitude operator (RAO) through AI technology. It used a neural network based on one of the types of AI methods. The data used in the neural network consisted of the properties of the vessel and RAO values, based on simulating the in-house code. The learning model consisted of an input layer, hidden layer, and output layer. The input layer comprised eight neurons, the hidden layer comprised the variables, and the output layer comprised 20 neurons. The RAO predicted with the neural network and an RAO created with the in-house code were compared. The accuracy was assessed and reviewed based on the root mean square error (RMSE), standard deviation (SD), random number change, correlation coefficient, and scatter plot. Finally, the optimal model was selected, and the conclusion was drawn. The ultimate goals of this study were to reduce the difficulty in the modeling work required to obtain the RAO, to reduce the difficulty in using commercial tools, and to enable an assessment of the stability of medium/small vessels in waves.

• Proceedings of the Korea Committee for Ocean Resources and Engineering Conference
• /
• 2003.10a
• /
• pp.340-345
• /
• 2003

This study, as a basic study for establishing a influence forecasting/estimating model when drain the deep sea water to the ocean after using it, carried out studies as follows; 1) estimating the amount of river discharge and pollutant loads inflowing into the developing region of deep sea water in East Sea, Korea 2) a field observation of tidal current, vertical distribution of water temperature and salinity, and 3-D numerical experiment of tidal current to analysis physical oceanographic status. The amount of river discharge flowing into the study area was estimated about $462.6{times}10^{3}m^{3}/day$ of daily mean in 2002 year. annual mean pollutant load of COD, TN and TP were estimated 7.02 ton-COD/day, 4.06 ton-TN/day and 0.39 ton/day, respectively. Field observation of tidal current results usually show about $20{\sim}40cm/sec$ of current velocity at the surface layer, it indicated a tendency that the current velocity decreases under 20cm/sec as the water depth increases. We could find a stratification within approximately the depth of 30m in field observation area, and the depth increases. We could find a stratification within approximately the depth of 30m in field observation area, and the differences of water temperature and salinity between the surface layer and bottom layer were about $18^{\circ}C$ and 0.8 psu, respectively. On the other hand, we found that there was a definite as the water mass of deep sea water about 34 psu of salinity.

• Journal of Ocean Engineering and Technology
• /
• v.19 no.1 s.62
• /
• pp.14-19
• /
• 2005

As a basic study for establishing the input conditions of a forecasting/estimating model, used for deep-sea water drainage to the ocean, this study was carried out as follows: 1) estimating the amount of river discharge and pollutant loads into the developing region of deep sea water in the East Sea, Korea, 2) a field observation of tidal current, vertical water temperature, and salinity distribution, 3) 3-D numerical experiment of tidal current to analyze the physical oceanographic status. The amount of river discharge flowing into this study area was estimated at about $462.7{\times}103 m\^3/day$ of daily mean in 2002. Annual mean pollutant load of COD, TN, and TP were estimated at 7.02 ton-COD/day, 4.06 ton-TN/day, and 0.39 ton/day, respectively. Field observation of tidal current normally shows 20-40cm/sec of current velocity at the surface layer, and it decreases under 20cm/sec as the water depth increases. We also found a stratification condition at around 30m water depth in the observation area. The differences in water temperature and salinity, between the surface layer and the bottom layer, were about 18 C and 0.8 psu, respectively. On the other hand, we found a definite trend of 34 psu salinity water mass in the deep sea region.

• Ocean and Polar Research
• /
• v.33 no.1
• /
• pp.55-68
• /
• 2011

The distribution and inter-annual variation of nutrients (N, P, Si) and dissolved/particulate organic carbon were investigated in the equatorial thermocline ridge ($7^{\circ}{\sim}11.5^{\circ}N$, $131.5^{\circ}W$) of the northeast Pacific. From the Oceanic Nino Index and Multivariate ENSO Index provided by NOAA, normal condition was observed in July 2003 and August 2005 on the aspect of global climate/ocean change. However, La Ni$\~{n}$a and El Ni$\~{n}$o episodes occurred in July 2007 and August 2009, respectively. Thermocline ridge in the study area was located at $9^{\circ}N$ in July 2003, $8^{\circ}N$ in August 2005, $10^{\circ}N$ in July 2007, and $10.5^{\circ}N$ in August 2009 under the influence of global climate/ocean change and surface current system (North Equatorial Counter Current and North Equatorial Current) of the northeast Pacific. Maximum depth integrated values (DIV) of nutrients in the upper layer (0~100 m depth range) were shown in July 2007 (mean 21.12 gN/$m^2$, 4.27 gP/$m^2$, 33.72 gSi/$m^2$) and higher variability of DIV in the equatorial thermocline ridge was observed at $10^{\circ}N$ during the study periods. Also, maximum concentration of dissolved organic carbon (DOC) in the upper 50 m depth layer was observed in July 2007 (mean $107.48{\pm}14.58\;{\mu}M$), and particulate organic carbon (POC, mean $9.42{\pm}3.02\;{\mu}M$) was similar to that of DOC. Nutrient concentration in the surface layer increased with effect of upwelling phenomenon in the equatorial thermocline ridge and La Ni$\~{n}$a episode, which had formed in the central Pacific. This process also resulted in the increasing of organic carbon concentration (DOC and POC) in the surface layer. From these results, it is suggested that spatial and temporal variation of chemical and biological factors were generated by physical processes in the equatorial thermocline ridge.

• Journal of Information Processing Systems
• /
• v.19 no.1
• /
• pp.98-108
• /
• 2023

This paper is an attempt to design segmentation method based on fully convolutional networks (FCN) and attention mechanism. The first five layers of the Visual Geometry Group (VGG) 16 network serve as the coding part in the semantic segmentation network structure with the convolutional layer used to replace pooling to reduce loss of image feature extraction information. The up-sampling and deconvolution unit of the FCN is then used as the decoding part in the semantic segmentation network. In the deconvolution process, the skip structure is used to fuse different levels of information and the attention mechanism is incorporated to reduce accuracy loss. Finally, the segmentation results are obtained through pixel layer classification. The results show that our method outperforms the comparison methods in mean pixel accuracy (MPA) and mean intersection over union (MIOU).

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.4
• /
• pp.161-167
• /
• 2019

Recently, demand forecasting techniques have been actively studied due to interest in stable power supply with surging power demand, and increase in spread of smart meters that enable real-time power measurement. In this study, we proceeded the deep learning prediction model experiments which learns actual measured power usage data of home and outputs the forecasting result. And we proceeded pre-processing with moving average method. The predicted value made by the model is evaluated with the actual measured data. Through this forecasting, it is possible to lower the power supply reserve ratio and reduce the waste of the unused power. In this paper, we conducted experiments on three types of networks: Multi Layer Perceptron (MLP), Recurrent Neural Network (RNN), and Long Short Term Memory (LSTM) and we evaluate the results of each scheme. Evaluation is conducted with following method: MSE(Mean Squared Error) method and MAE(Mean Absolute Error).

• International Journal of Contents
• /
• v.13 no.4
• /
• pp.23-28
• /
• 2017

Of the total economic loss caused by disasters, 40% are due to floods and floods have a severe impact on human health and life. So, it is important to monitor the water level of a river and to issue a flood warning during unfavorable circumstances. In this paper, we propose a modified error function to improve a hydrological modeling using a multi-layer perceptron (MLP) neural network. When MLP's are trained to minimize the conventional mean-squared error function, the prediction performance is poor because MLP's are highly tunned to training data. Our goal is achieved by preventing overspecialization to training data, which is the main reason for performance degradation for rare or test data. Based on the modified error function, an MLP is trained to predict the water level with rainfall data at upper reaches. Through simulations to predict the water level of Nakdong River near a UNESCO World Heritage Site "Hahoe Village," we verified that the prediction performance of MLP with the modified error function is superior to that with the conventional mean-squared error function, especially maximum error of 40.85cm vs. 55.51cm.

• Journal of Korean Association for Spatial Structures
• /
• v.23 no.3
• /
• pp.87-94
• /
• 2023

Chloride is one of the most common threats to reinforced concrete (RC) durability. Alkaline environment of concrete makes a passive layer on the surface of reinforcement bars that prevents the bar from corrosion. However, when the chloride concentration amount at the reinforcement bar reaches a certain level, deterioration of the passive protection layer occurs, causing corrosion and ultimately reducing the structure's safety and durability. Therefore, understanding the chloride diffusion and its prediction are important to evaluate the safety and durability of RC structure. In this study, the chloride diffusion coefficient is predicted by machine learning techniques. Various machine learning techniques such as multiple linear regression, decision tree, random forest, support vector machine, artificial neural networks, extreme gradient boosting annd k-nearest neighbor were used and accuracy of there models were compared. In order to evaluate the accuracy, root mean square error (RMSE), mean square error (MSE), mean absolute error (MAE) and coefficient of determination (R2) were used as prediction performance indices. The k-fold cross-validation procedure was used to estimate the performance of machine learning models when making predictions on data not used during training. Grid search was applied to hyperparameter optimization. It has been shown from numerical simulation that ensemble learning methods such as random forest and extreme gradient boosting successfully predicted the chloride diffusion coefficient and artificial neural networks also provided accurate result.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.1
• /
• pp.23-28
• /
• 2021

Data analysis research using deep learning has recently been studied in various field. In this paper, we conduct a GNSS (Global Navigation Satellite System)-based meteorological study applying deep learning by estimating the ZWD (Zenith tropospheric Wet Delay) through MLP (Multi-Layer Perceptron) and LSTM (Long Short-Term Memory) models. Deep learning models were trained with meteorological data and ZWD which is estimated using zenith tropospheric total delay and dry delay. We apply meteorological data not used for learning to the learned model to estimate ZWD with centimeter-level RMSE (Root Mean Square Error) in both models. It is necessary to analyze the GNSS data from coastal areas together and increase time resolution in order to estimate ZWD in various situations.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.21 no.6
• /
• pp.341-350
• /
• 1988

The wind stress distribution over the East Sea of Korea was obtained from the shipboard observations of the Fisheries Research and Development Agency along the serial observation lines. These monthly and annual mean wind stress distributions were put into the simplified interface model which describes the latitudinal variations of the upper-layer thickness as function of the curl of the wind stress. The observed variations of the surface, zonally averaged winds indeed caused the upper-layer flow convergent and divergent at the latitudes that produced a tone of thick upper-layer or a deep permanent thermocline and the shallower depth with divergence. Thus, the wind field contributes positively to maintain the almost time-independent distribution of the interface of 'saddle like' feature in north-south direction over the study area.